Many studies have been done on predicting students’ academic performance over several years. A key indicator of education quality is student performance. In educational institutions, huge amount of data is stored about the students that can be explored to learn more about how they are learning and using data mining methods, to enhance their performance in advance. Machine learning algorithms, including KNN, Naïve Bayes, Decision Tree, ANN, Logistic Regression and Support vector machine, have been widely utilized in these studies, encompassing supervised, unsupervised, and semisupervised learning approaches. The main focus of the study is to identify the most suitable methods for predicting the performance of students from the institutes of Jalandhar. The sample size is 280 respondents of either male or female across Jalandhar. They belong to different classes of schools in Jalandhar city. In this paper, we will look for elements that could improve or help pupils perform better. In this we present the systematic literature review of 30 papers from Google scholar which helps to predict the factors that affecting on students’ academic performance Mean is used for descriptive data analysis, Pearson’s Correlation is used get the relation between attributes. T-Test and ANOVA are used for Hypothesis testing. All the experiments were conducted on GoogleColab and RapidMiner Studio tool.